StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledge precisely. Finally, StructVPR achieves impressive performance on several benchmarks using only global retrieval and even outperforms many two-stage approaches by a large margin. After adding additional re-ranking, ours achieves state-of-the-art performance while maintaining a low computational cost.

Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning

Due to the representation limitation of the joint Q value function, multi-agent reinforcement learning methods with linear value decomposition (LVD) or monotonic value decomposition (MVD) suffer from relative overgeneralization. As a result, they can not ensure optimal consistency (i.e., the correspondence between individual greedy actions and the maximal true Q value). In this paper, we derive the expression of the joint Q value function of LVD and MVD. According to the expression, we draw a transition diagram, where each self-transition node (STN) is a possible convergence. To ensure optimal consistency, the optimal node is required to be the unique STN. Therefore, we propose the greedy-based value representation (GVR), which turns the optimal node into an STN via inferior target shaping and further eliminates the non-optimal STNs via superior experience replay. In addition, GVR achieves an adaptive trade-off between optimality and stability. Our method outperforms state-of-the-art baselines in experiments on various benchmarks. Theoretical proofs and empirical results on matrix games demonstrate that GVR ensures optimal consistency under sufficient exploration.

Could Giant Pretrained Image Models Extract Universal Representations?

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which is problematic in computer vision where tasks vary significantly in input/output format and the type of information that is of value. In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition. From this empirical analysis, our work answers the questions of what pretraining task fits best with this frozen setting, how to make the frozen setting more flexible to various downstream tasks, and the effect of larger model sizes. We additionally examine the upper bound of performance using a giant frozen pretrained model with 3 billion parameters (SwinV2-G) and find that it reaches competitive performance on a varied set of major benchmarks with only one shared frozen base network: 60.0 box mAP and 52.2 mask mAP on COCO object detection test-dev, 57.6 val mIoU on ADE20K semantic segmentation, and 81.7 top-1 accuracy on Kinetics-400 action recognition. With this work, we hope to bring greater attention to this promising path of freezing pretrained image models.

Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios

In this paper, we propose a lightweight system, RDS-SLAM, based on ORB-SLAM2, which can accurately estimate poses and build semantic maps at object level for dynamic scenarios in real time using only one commonly used Intel Core i7 CPU. In RDS-SLAM, three major improvements, as well as major architectural modifications, are proposed to overcome the limitations of ORB-SLAM2. Firstly, it adopts a lightweight object detection neural network in key frames. Secondly, an efficient tracking and prediction mechanism is embedded into the system to remove the feature points belonging to movable objects in all incoming frames. Thirdly, a semantic octree map is built by probabilistic fusion of detection and tracking results, which enables a robot to maintain a semantic description at object level for potential interactions in dynamic scenarios. We evaluate RDS-SLAM in TUM RGB-D dataset, and experimental results show that RDS-SLAM can run with 30.3 ms per frame in dynamic scenarios using only an Intel Core i7 CPU, and achieves comparable accuracy compared with the state-of-the-art SLAM systems which heavily rely on both Intel Core i7 CPUs and powerful GPUs.

Finetuning Pretrained Vision-Language Models with Correlation Information Bottleneck for Robust Visual Question Answering

Benefiting from large-scale Pretrained Vision-Language Models (VL-PMs), the performance of Visual Question Answering (VQA) has started to approach human oracle performance. However, finetuning large-scale VL-PMs with limited data for VQA usually faces overfitting and poor generalization issues, leading to a lack of robustness. In this paper, we aim to improve the robustness of VQA systems (ie, the ability of the systems to defend against input variations and human-adversarial attacks) from the perspective of Information Bottleneck when finetuning VL-PMs for VQA. Generally, internal representations obtained by VL-PMs inevitably contain irrelevant and redundant information for the downstream VQA task, resulting in statistically spurious correlations and insensitivity to input variations. To encourage representations to converge to a minimal sufficient statistic in vision-language learning, we propose the Correlation Information Bottleneck (CIB) principle, which seeks a tradeoff between representation compression and redundancy by minimizing the mutual information (MI) between the inputs and internal representations while maximizing the MI between the outputs and the representations. Meanwhile, CIB measures the internal correlations among visual and linguistic inputs and representations by a symmetrized joint MI estimation. Extensive experiments on five VQA benchmarks of input robustness and two VQA benchmarks of human-adversarial robustness demonstrate the effectiveness and superiority of the proposed CIB in improving the robustness of VQA systems.

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rules, making difficult to handle complicated scenes. Different from them, we propose a Dynamic Ball Query (DBQ) network to adaptively select a subset of input points according to the input features, and assign the feature transform with suitable receptive field for each selected point. It can be embedded into some state-of-the-art 3D detectors and trained in an end-to-end manner, which significantly reduces the computational cost. Extensive experiments demonstrate that our method can reduce latency by 30%-60% on KITTI and Waymo datasets. Specifically, the inference speed of our detector can reach 162 FPS and 30 FPS with negligible performance degradation on KITTI and Waymo datasets, respectively.

Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer from these co-occurring ingredients which often dominate the actual action content in videos. In this paper, we explore two orthogonal but complementary aspects of a video snippet, i.e., the action features and the co-occurrence features. Especially, we develop a novel auxiliary task by decoupling these two types of features within a video snippet and recombining them to generate a new feature representation with more salient action information for accurate action localization. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features, and then synthesizes a new action-dominated video representation. Extensive experimental results and ablation studies on THUMOS14 and ActivityNet v1.3 demonstrate that our new representation, combined with a simple action detector, can significantly improve the action localization performance.

Social Interpretable Tree for Pedestrian Trajectory Prediction

Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications. In this paper, we propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task, where a hand-crafted tree is built depending on the prior information of observed trajectory to model multiple future trajectories. Specifically, a path in the tree from the root to leaf represents an individual possible future trajectory. SIT employs a coarse-to-fine optimization strategy, in which the tree is first built by high-order velocity to balance the complexity and coverage of the tree and then optimized greedily to encourage multimodality. Finally, a teacher-forcing refining operation is used to predict the final fine trajectory. Compared with prior methods which leverage implicit latent variables to represent possible future trajectories, the path in the tree can explicitly explain the rough moving behaviors (e.g., go straight and then turn right), and thus provides better interpretability. Despite the hand-crafted tree, the experimental results on ETH-UCY and Stanford Drone datasets demonstrate that our method is capable of matching or exceeding the performance of state-of-the-art methods. Interestingly, the experiments show that the raw built tree without training outperforms many prior deep neural network based approaches. Meanwhile, our method presents sufficient flexibility in long-term prediction and different best-of-$K$ predictions.

Test-time Batch Normalization

Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift. In this paper, targeting of alleviating distribution shift in test time, we revisit the batch normalization (BN) in the training process and reveals two key insights benefiting test-time optimization: $(i)$ preserving the same gradient backpropagation form as training, and $(ii)$ using dataset-level statistics for robust optimization and inference. Based on the two insights, we propose a novel test-time BN layer design, GpreBN, which is optimized during testing by minimizing Entropy loss. We verify the effectiveness of our method on two typical settings with distribution shift, i.e., domain generalization and robustness tasks. Our GpreBN significantly improves the test-time performance and achieves the state of the art results.

Visual Concepts Tokenization

Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene decomposition. Towards this goal, we propose an unsupervised transformer-based Visual Concepts Tokenization framework, dubbed VCT, to perceive an image into a set of disentangled visual concept tokens, with each concept token responding to one type of independent visual concept. Particularly, to obtain these concept tokens, we only use cross-attention to extract visual information from the image tokens layer by layer without self-attention between concept tokens, preventing information leakage across concept tokens. We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts. The cross-attention and disentangling loss play the role of induction and mutual exclusion for the concept tokens, respectively. Extensive experiments on several popular datasets verify the effectiveness of VCT on the tasks of disentangled representation learning and scene decomposition. VCT achieves the state of the art results by a large margin.